Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Anomaly detection and segmentation in carotid ultrasound images using Hybrid Stable AnoGAN
Umeå University, Faculty of Medicine, Department of Diagnostics and Intervention.
Umeå University, Faculty of Medicine, Department of Diagnostics and Intervention.ORCID iD: 0000-0003-3363-7414
Umeå University, Faculty of Medicine, Department of Public Health and Clinical Medicine.ORCID iD: 0000-0003-4100-8298
Umeå University, Faculty of Medicine, Department of Diagnostics and Intervention.ORCID iD: 0000-0003-4288-1208
2025 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 13, p. 167014-167033Article in journal (Refereed) Published
Abstract [en]

Detecting and segmenting arterial plaques in ultrasound images is essential for the early diagnosis and prevention of cardiovascular diseases. This paper presents Hybrid Stable AnoGAN (HS-AnoGAN), an enhanced anomaly detection framework based on AnoGAN (Anomaly Generative Adversarial Network), which utilizes generative adversarial learning to model normal anatomical structures and identify abnormal regions indicative of pathology. The proposed approach introduces key improvements, including direct latent space encoding, hybrid reconstruction loss, feature matching in the discriminator, and adaptive thresholding, leading to more precise anomaly localization. Additionally, spectral normalization and Wasserstein loss with gradient penalty are incorporated to improve training stability and prevent mode collapse. To the best of our knowledge, this is the first attempt to apply anomaly detection techniques for arterial plaque detection and segmentation in ultrasound images. Comparative experiments demonstrate that HS-AnoGAN outperforms state-of-the-art methods, achieving a 9.8% increase in detection accuracy, and a 7.5% enhancement in Dice score for segmentation quality. These results highlight the effectiveness of HS-AnoGAN in improving both plaque detection and segmentation in ultrasound imaging, making it a promising tool for clinical applications.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2025. Vol. 13, p. 167014-167033
Keywords [en]
Anomaly detection, atherosclerosis, carotid ultrasound, generative adversarial networks, medical imaging, plaque segmentation
National Category
Medical Imaging
Identifiers
URN: urn:nbn:se:umu:diva-244758DOI: 10.1109/ACCESS.2025.3611327Scopus ID: 2-s2.0-105016716721OAI: oai:DiVA.org:umu-244758DiVA, id: diva2:2003224
Funder
Norrländska HjärtfondenThe Kempe Foundations, JCK-3172Available from: 2025-10-03 Created: 2025-10-03 Last updated: 2025-10-03Bibliographically approved

Open Access in DiVA

fulltext(2140 kB)205 downloads
File information
File name FULLTEXT01.pdfFile size 2140 kBChecksum SHA-512
493cde267b19b71d612160428474b155bdedbaa8bf05bdb74e980770ae6b115b765a3cdf550e18d69b5d25ace601004a071e6f2dd8e650c94fcb9f13de5817b0
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Saboori, ArashÖhberg, FredrikNäslund, UlfGrönlund, Christer

Search in DiVA

By author/editor
Saboori, ArashÖhberg, FredrikNäslund, UlfGrönlund, Christer
By organisation
Department of Diagnostics and InterventionDepartment of Public Health and Clinical Medicine
In the same journal
IEEE Access
Medical Imaging

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 354 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf